Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    suffrage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     düny
    -0.07
    　　　　　　 　
    -0.07
    TIME
    -0.07
     misconception
    -0.07
     WAY
    -0.06
    (service
    -0.06
    _birth
    -0.06
    神
    -0.06
    .toJSONString
    -0.06
    TYPE
    -0.06
    POSITIVE LOGITS
     marked
    0.07
     dracon
    0.07
    _IDS
    0.06
     �
    0.06
     disturbances
    0.06
     curb
    0.06
    _predict
    0.06
     vigor
    0.06
    /auth
    0.06
    _sock
    0.06
    Act Density 0.007%

    No Known Activations